def getValidationDataset(self):
print "Reading the valid pairs"
valid = data_io.read_valid_pairs()
valid2 = data_io.read_valid_info()
valid["A type"] = valid2["A type"]
valid["B type"] = valid2["B type"]
return valid
def getDataset(self):
if self.getTrain:
readData = data_io.read_train_pairs()
readData2 = data_io.read_train_info()
else:
readData = data_io.read_valid_pairs()
readData2 = data_io.read_valid_info()
readData["A type"] = readData2["A type"]
readData["B type"] = readData2["B type"]
return readData
def getDataset(self):
if self.getTrain:
readData = data_io.read_train_pairs()
readData2 = data_io.read_train_info()
else:
readData = data_io.read_valid_pairs()
readData2 = data_io.read_valid_info()
readData["A type"] = readData2["A type"]
readData["B type"] = readData2["B type"]
return readData
def main():
print("Reading the valid pairs")
valid = data_io.read_valid_pairs()
valid_info = data_io.read_valid_info()
valid = pd.concat([valid, valid_info],axis =1)
valid = train.get_types(valid)
print("Loading the classifier")
classifier = data_io.load_model()
print("Making predictions")
predictions = classifier.predict(valid)
predictions = predictions.flatten()
print("Writing predictions to file")
data_io.write_submission(predictions, fn)
def main():
print("Reading the valid pairs")
valid = data_io.read_valid_pairs()
features = fe.feature_extractor()
print("Transforming features")
trans_valid = features.fit_transform(valid)
trans_valid = np.nan_to_num(trans_valid)
print("Saving Valid Features")
data_io.save_valid_features(trans_valid)
print("Loading the classifier")
#(both_classifier, A_classifier, B_classifier, none_classifier) = data_io.load_model()
classifier = data_io.load_model()
print("Making predictions")
valid_info = data_io.read_valid_info()
predictions = list()
curr_pred = None
"""
for i in range(len(trans_valid)):
if valid_info["A type"][i] == "Numerical" and valid_info["B type"][i] == "Numerical":
curr_pred = both_classifier.predict_proba(trans_valid[i, :])
elif valid_info["A type"][i] == "Numerical" and valid_info["B type"][i] != "Numerical":
curr_pred = A_classifier.predict_proba(trans_valid[i, :])
elif valid_info["A type"][i] != "Numerical" and valid_info["B type"][i] == "Numerical":
curr_pred = B_classifier.predict_proba(trans_valid[i, :])
else:
curr_pred = none_classifier.predict_proba(trans_valid[i, :])
predictions.append(curr_pred[0][2] - curr_pred[0][0])
"""
orig_predictions = classifier.predict_proba(trans_valid)
predictions = orig_predictions[:, 2] - orig_predictions[:, 0]
predictions = predictions.flatten()
print("Writing predictions to file")
data_io.write_submission(predictions)
def main():
print("Reading the valid pairs")
valid = data_io.read_valid_pairs()
features = fe.feature_extractor()
print("Transforming features")
trans_valid = features.fit_transform(valid)
trans_valid = np.nan_to_num(trans_valid)
print("Saving Valid Features")
data_io.save_valid_features(trans_valid)
print("Loading the classifier")
#(both_classifier, A_classifier, B_classifier, none_classifier) = data_io.load_model()
classifier = data_io.load_model()
print("Making predictions")
valid_info = data_io.read_valid_info()
predictions = list()
curr_pred = None
"""
for i in range(len(trans_valid)):
if valid_info["A type"][i] == "Numerical" and valid_info["B type"][i] == "Numerical":
curr_pred = both_classifier.predict_proba(trans_valid[i, :])
elif valid_info["A type"][i] == "Numerical" and valid_info["B type"][i] != "Numerical":
curr_pred = A_classifier.predict_proba(trans_valid[i, :])
elif valid_info["A type"][i] != "Numerical" and valid_info["B type"][i] == "Numerical":
curr_pred = B_classifier.predict_proba(trans_valid[i, :])
else:
curr_pred = none_classifier.predict_proba(trans_valid[i, :])
predictions.append(curr_pred[0][2] - curr_pred[0][0])
"""
orig_predictions = classifier.predict_proba(trans_valid)
predictions = orig_predictions[:, 2] - orig_predictions[:, 0]
predictions = predictions.flatten()
print("Writing predictions to file")
data_io.write_submission(predictions)
def extract_valid_features():
start = time.time()
features = feature_extractor()
header = []
for h in features.features:
header.append(h[0])
print("Reading the valid pairs")
X = data_io.read_valid_pairs()
print("Extracting features")
# well, no fit data, so y = None
extracted = features.fit_transform(X,y = None,type_map = data_io.read_valid_info())
elapsed = float(time.time() - start)
print("Features extracted in " + str(elapsed/60.0) + " Minutes")
print ("Saving features")
X = pd.DataFrame(extracted, index = X.index)
X.columns = header
data_io.save_valid_features(X)
def extract_valid_features():
start = time.time()
features = feature_extractor()
header = []
for h in features.features:
header.append(h[0])
print("Reading the valid pairs")
X = data_io.read_valid_pairs()
print("Extracting features")
# well, no fit data, so y = None
extracted = features.fit_transform(X,
y=None,
type_map=data_io.read_valid_info())
elapsed = float(time.time() - start)
print("Features extracted in " + str(elapsed / 60.0) + " Minutes")
print("Saving features")
X = pd.DataFrame(extracted, index=X.index)
X.columns = header
data_io.save_valid_features(X)
probb_nz = probb[np.nonzero(probb)]
jointp = np.outer(proba_nz, probb_nz)
hpos = np.sum(np.log(jointp) * jointp)
return -hpos
if __name__ == '__main__':
print 'Reading in {} data...'.format(DATA)
if DATA == 'train':
info = data_io.read_train_info()
train = data_io.read_train_pairs()
elif DATA == 'valid':
info = data_io.read_valid_info()
train = data_io.read_valid_pairs()
else:
raise ValueError
print 'Saving coded info matrix...'
codes = np.zeros(info.values.shape)
lookup = {'Numerical': 1, 'Categorical': 2, 'Binary': 3}
for i, t in enumerate(info.values):
a, b = t
codes[i, :] = [lookup[a], lookup[b]]
savemat('matlab/{}info.mat'.format(DATA), {'codes': codes},
oned_as='column')
print 'Saving value matrices...'
probb_nz = probb[np.nonzero(probb)]
jointp = np.outer(proba_nz, probb_nz)
hpos = np.sum(np.log(jointp) * jointp)
return -hpos
if __name__ == "__main__":
print "Reading in {} data...".format(DATA)
if DATA == "train":
info = data_io.read_train_info()
train = data_io.read_train_pairs()
elif DATA == "valid":
info = data_io.read_valid_info()
train = data_io.read_valid_pairs()
else:
raise ValueError
print "Saving coded info matrix..."
codes = np.zeros(info.values.shape)
lookup = {"Numerical": 1, "Categorical": 2, "Binary": 3}
for i, t in enumerate(info.values):
a, b = t
codes[i, :] = [lookup[a], lookup[b]]
savemat("matlab/{}info.mat".format(DATA), {"codes": codes}, oned_as="column")
print "Saving value matrices..."
for i, t in enumerate(train.values):